Assessing driving plans for autonomous vehicles
AssigneeWaymo LLC
InventorsLeif Morgan Johnson, Johan Engstrom, Azadeh Dinparastdjadid, Isaac John Supeene
Life of this patent
Estimating the term…
Abstract
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for assessing driving plans for autonomous vehicles. One of the methods includes obtaining data representing a goal for an agent in a driving environment, generating one or more available trajectories for the agent, and selecting one or more future actions for the agent.
Claims21
A computer-implemented method comprising:
- obtaining data representing a goal for an agent in a driving environment;
- generating one or more available trajectories for the agent to attain the goal in the driving environment;
- selecting one or more future actions for the agent, comprising:
- for each of the one or more available trajectories, determining an epistemic value that represents the degree of information to be gained about the driving environment and a pragmatic value that represents the degree to which the agent will advance toward the goal;
- determining a trajectory of the one or more available trajectories that is optimized between the epistemic value and the pragmatic value;
- and
- selecting the one or more future actions based on the trajectory that is optimized between the epistemic value and the pragmatic value;
- and
- causing the agent to execute the one or more future actions.
A system comprising:
- one or more computers;
- and
- one or more storage devices storing instructions that are operable, when executed by the one or more computers, cause the one or more computers to perform operations comprising:
- obtaining data representing a goal for an agent in a driving environment;
- generating one or more available trajectories for the agent to attain the goal in the driving environment;
- selecting one or more future actions for the agent, comprising:
- for each of the one or more available trajectories, determining an epistemic value that represents the degree of information to be gained about the driving environment and a pragmatic value that represents the degree to which the agent will advance toward the goal;
- determining a trajectory of the one or more available trajectories that is optimized between the epistemic value and the pragmatic value;
- and
- selecting the one or more future actions based on the trajectory that is optimized between the epistemic value and the pragmatic value;
- and
- causing the agent to execute the one or more future actions.
One or more non-transitory storage media storing instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:
- obtaining data representing a goal for an agent in a driving environment;
- generating one or more available trajectories for the agent to attain the goal in the driving environment;
- selecting one or more future actions for the agent, comprising:
- for each of the one or more available trajectories, determining an epistemic value that represents the degree of information to be gained about the driving environment and a pragmatic value that represents the degree to which the agent will advance toward the goal;
- determining a trajectory of the one or more available trajectories that is optimized between the epistemic value and the pragmatic value;
- and
- selecting the one or more future actions based on the trajectory that is optimized between the epistemic value and the pragmatic value;
- and
- causing the agent to execute the one or more future actions.
Dependencies are inferred from the claim text.